commit 75f027041d1b1962867d38e7aa08265153d83071 Author: ModelHub XC Date: Sat May 23 21:28:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/SmolLM-1.7B-Instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..482ec72 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,50 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +SmolLM-1.7B-Instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +SmolLM-1.7B-Instruct.f16.gguf filter=lfs diff=lfs merge=lfs -text +SmolLM-1.7B-Instruct.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +SmolLM-1.7B-Instruct.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +SmolLM-1.7B-Instruct.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +SmolLM-1.7B-Instruct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +SmolLM-1.7B-Instruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +SmolLM-1.7B-Instruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +SmolLM-1.7B-Instruct.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +SmolLM-1.7B-Instruct.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +SmolLM-1.7B-Instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +SmolLM-1.7B-Instruct.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +SmolLM-1.7B-Instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +SmolLM-1.7B-Instruct.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +SmolLM-1.7B-Instruct.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..a16f2b2 --- /dev/null +++ b/README.md @@ -0,0 +1,76 @@ +--- +base_model: HuggingFaceTB/SmolLM-1.7B-Instruct +datasets: +- Magpie-Align/Magpie-Pro-300K-Filtered +- bigcode/self-oss-instruct-sc2-exec-filter-50k +- teknium/OpenHermes-2.5 +- HuggingFaceTB/everyday-conversations-llama3.1-2k +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- alignment-handbook +- trl +- sft +--- +## About + + + + + + +static quants of https://huggingface.co/HuggingFaceTB/SmolLM-1.7B-Instruct + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/SmolLM-1.7B-Instruct-i1-GGUF +## Usage + +If you are unsure how to use GGUF files, refer to one of [TheBloke's +READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for +more details, including on how to concatenate multi-part files. + +## Provided Quants + +(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) + +| Link | Type | Size/GB | Notes | +|:-----|:-----|--------:|:------| +| [GGUF](https://huggingface.co/mradermacher/SmolLM-1.7B-Instruct-GGUF/resolve/main/SmolLM-1.7B-Instruct.Q2_K.gguf) | Q2_K | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/SmolLM-1.7B-Instruct-GGUF/resolve/main/SmolLM-1.7B-Instruct.IQ3_XS.gguf) | IQ3_XS | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/SmolLM-1.7B-Instruct-GGUF/resolve/main/SmolLM-1.7B-Instruct.IQ3_S.gguf) | IQ3_S | 0.9 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/SmolLM-1.7B-Instruct-GGUF/resolve/main/SmolLM-1.7B-Instruct.Q3_K_S.gguf) | Q3_K_S | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/SmolLM-1.7B-Instruct-GGUF/resolve/main/SmolLM-1.7B-Instruct.IQ3_M.gguf) | IQ3_M | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/SmolLM-1.7B-Instruct-GGUF/resolve/main/SmolLM-1.7B-Instruct.Q3_K_M.gguf) | Q3_K_M | 1.0 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/SmolLM-1.7B-Instruct-GGUF/resolve/main/SmolLM-1.7B-Instruct.Q3_K_L.gguf) | Q3_K_L | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/SmolLM-1.7B-Instruct-GGUF/resolve/main/SmolLM-1.7B-Instruct.IQ4_XS.gguf) | IQ4_XS | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/SmolLM-1.7B-Instruct-GGUF/resolve/main/SmolLM-1.7B-Instruct.Q4_K_S.gguf) | Q4_K_S | 1.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/SmolLM-1.7B-Instruct-GGUF/resolve/main/SmolLM-1.7B-Instruct.Q4_K_M.gguf) | Q4_K_M | 1.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/SmolLM-1.7B-Instruct-GGUF/resolve/main/SmolLM-1.7B-Instruct.Q5_K_S.gguf) | Q5_K_S | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/SmolLM-1.7B-Instruct-GGUF/resolve/main/SmolLM-1.7B-Instruct.Q5_K_M.gguf) | Q5_K_M | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/SmolLM-1.7B-Instruct-GGUF/resolve/main/SmolLM-1.7B-Instruct.Q6_K.gguf) | Q6_K | 1.5 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/SmolLM-1.7B-Instruct-GGUF/resolve/main/SmolLM-1.7B-Instruct.Q8_0.gguf) | Q8_0 | 1.9 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/SmolLM-1.7B-Instruct-GGUF/resolve/main/SmolLM-1.7B-Instruct.f16.gguf) | f16 | 3.5 | 16 bpw, overkill | + +Here is a handy graph by ikawrakow comparing some lower-quality quant +types (lower is better): + +![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png) + +And here are Artefact2's thoughts on the matter: +https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 + +## FAQ / Model Request + +See https://huggingface.co/mradermacher/model_requests for some answers to +questions you might have and/or if you want some other model quantized. + +## Thanks + +I thank my company, [nethype GmbH](https://www.nethype.de/), for letting +me use its servers and providing upgrades to my workstation to enable +this work in my free time. + + diff --git a/SmolLM-1.7B-Instruct.IQ3_M.gguf b/SmolLM-1.7B-Instruct.IQ3_M.gguf new file mode 100644 index 0000000..b485c75 --- /dev/null +++ b/SmolLM-1.7B-Instruct.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:995fa0c3b8ae157b3f488df591ad73efc1cea2c2d4f41a2d8ac5a3cfdbb37dcd +size 810243008 diff --git a/SmolLM-1.7B-Instruct.IQ3_S.gguf b/SmolLM-1.7B-Instruct.IQ3_S.gguf new file mode 100644 index 0000000..84c71ff --- /dev/null +++ b/SmolLM-1.7B-Instruct.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:703c3827006ab02aef0db9f68d4458bc66fd6f2964a06ff14eedd67261c01499 +size 776819648 diff --git a/SmolLM-1.7B-Instruct.IQ3_XS.gguf b/SmolLM-1.7B-Instruct.IQ3_XS.gguf new file mode 100644 index 0000000..9a98b24 --- /dev/null +++ b/SmolLM-1.7B-Instruct.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dba9f3e643909905759cf1133007873ec642aad7abd63971b6073420b86bf4b9 +size 739070912 diff --git a/SmolLM-1.7B-Instruct.IQ4_XS.gguf b/SmolLM-1.7B-Instruct.IQ4_XS.gguf new file mode 100644 index 0000000..1e30557 --- /dev/null +++ b/SmolLM-1.7B-Instruct.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:54daf1520e654159b3531426703fd61bfec5acee6f2f2f0c986b4735cc94882c +size 948261824 diff --git a/SmolLM-1.7B-Instruct.Q2_K.gguf b/SmolLM-1.7B-Instruct.Q2_K.gguf new file mode 100644 index 0000000..23fb43c --- /dev/null +++ b/SmolLM-1.7B-Instruct.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d25108ab944ac4ba6fe120b2ea9b6b722701d97326979c3b14665064df60b334 +size 674583488 diff --git a/SmolLM-1.7B-Instruct.Q3_K_L.gguf b/SmolLM-1.7B-Instruct.Q3_K_L.gguf new file mode 100644 index 0000000..92da964 --- /dev/null +++ b/SmolLM-1.7B-Instruct.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f9bb17bc0c1eb6ea7c6996833fe9141ba4d3a69efdd697fc38f699d7b52c62e +size 932533184 diff --git a/SmolLM-1.7B-Instruct.Q3_K_M.gguf b/SmolLM-1.7B-Instruct.Q3_K_M.gguf new file mode 100644 index 0000000..650e332 --- /dev/null +++ b/SmolLM-1.7B-Instruct.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d7bfa15ae67c6f819a06405d11478f68d95676fcd6fac5405cd61e455c213c1b +size 860181440 diff --git a/SmolLM-1.7B-Instruct.Q3_K_S.gguf b/SmolLM-1.7B-Instruct.Q3_K_S.gguf new file mode 100644 index 0000000..eecb628 --- /dev/null +++ b/SmolLM-1.7B-Instruct.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:41781f489219ab1dd56e002ddf02cd4e28cb6c7abb1de5f9a1e81820954ebffd +size 776819648 diff --git a/SmolLM-1.7B-Instruct.Q4_K_M.gguf b/SmolLM-1.7B-Instruct.Q4_K_M.gguf new file mode 100644 index 0000000..6a4e31e --- /dev/null +++ b/SmolLM-1.7B-Instruct.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:93b08c86aa08f111ac51add4633675c730beefab68ce79231d1835b6a95cbdb3 +size 1055609792 diff --git a/SmolLM-1.7B-Instruct.Q4_K_S.gguf b/SmolLM-1.7B-Instruct.Q4_K_S.gguf new file mode 100644 index 0000000..1c076fe --- /dev/null +++ b/SmolLM-1.7B-Instruct.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3dc85caf1a5e15a59b1794fafcceeaba787df8692d82f81fe72c2f7785bea972 +size 999117760 diff --git a/SmolLM-1.7B-Instruct.Q5_K_M.gguf b/SmolLM-1.7B-Instruct.Q5_K_M.gguf new file mode 100644 index 0000000..7b42120 --- /dev/null +++ b/SmolLM-1.7B-Instruct.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:033f020859cf0d42373a5c3f13e2476290e4e8347a711b15073506cc37870482 +size 1225479104 diff --git a/SmolLM-1.7B-Instruct.Q5_K_S.gguf b/SmolLM-1.7B-Instruct.Q5_K_S.gguf new file mode 100644 index 0000000..d7720dd --- /dev/null +++ b/SmolLM-1.7B-Instruct.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4130ee171cc89c40cb72f0c8a847c11f1d453c3979bfd85d20b71336b0b92570 +size 1192055744 diff --git a/SmolLM-1.7B-Instruct.Q6_K.gguf b/SmolLM-1.7B-Instruct.Q6_K.gguf new file mode 100644 index 0000000..42af9f7 --- /dev/null +++ b/SmolLM-1.7B-Instruct.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3fdb6caaf6d3fa85123fbf16783c550d7d8fdc0538e091ec06213d5c8e60b29d +size 1405965248 diff --git a/SmolLM-1.7B-Instruct.Q8_0.gguf b/SmolLM-1.7B-Instruct.Q8_0.gguf new file mode 100644 index 0000000..6050045 --- /dev/null +++ b/SmolLM-1.7B-Instruct.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a7fa3f03bb90764003c0035b4842abc1081d560921734cbc542500e3c61ff552 +size 1820414912 diff --git a/SmolLM-1.7B-Instruct.f16.gguf b/SmolLM-1.7B-Instruct.f16.gguf new file mode 100644 index 0000000..a29388f --- /dev/null +++ b/SmolLM-1.7B-Instruct.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a1f31b1fc0d6e180c3ca0d794b85cb8ba598eb0a845ed493cd66f4a329691b5e +size 3424736192